evalops

Use when changing Maestro runtime, hosted runner, event contracts, migration packaging, or internal-to-public mirror behavior.

Triage production incidents by building a timeline, scoping blast radius, identifying mitigations, and preserving evidence. Use when the user asks about an outage, regression, alert, Sentry issue, or incident follow-up.

Install automated Maestro code review in a GitHub repository's CI — add a pull_request workflow that runs `maestro exec` and posts a merge-readiness review as a PR comment. Use when the user wants to set up automated PR review, wire Maestro into CI/CD, or "install code review".

Correctness-first, depth-first security audit of a single repository using STRIDE, OWASP Top 10, the OWASP LLM Top 10, and supply-chain analysis. Use when the user asks for a security review, a vulnerability audit, a threat model, or a pre-release security pass.

Review GitHub pull requests for correctness, regressions, missing tests, and merge readiness. Use when the user asks for PR review, review feedback, or a pre-merge risk pass.

Verify release readiness and post-release health from PRs, CI, tags, deploy evidence, rollback notes, and operator artifacts. Use when the user asks whether a release can ship, has shipped, or is safe to promote.

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This skill helps an LLM generate correct AxAgent tuning and evaluation code using @ax-llm/ax. Use when the user asks about agent.optimize(...), judgeOptions, eval datasets, optimization targets, saved optimizedProgram artifacts, or recursive optimization guidance.

This skill helps an LLM generate correct AxAgent code using @ax-llm/ax. Use when the user asks about agent(), child agents, namespaced functions, discovery mode, shared fields, llmQuery(...), RLM code execution, recursionOptions, or agent runtime behavior. For tuning and eval with agent.optimize(...), use ax-agent-optimize.

This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax. Use when the user asks about ai(), providers, models, presets, embeddings, extended thinking, context caching, or mentions OpenAI/Anthropic/Google/Azure/Groq/DeepSeek/Mistral/Cohere/Together/Ollama/HuggingFace/Reka/OpenRouter with @ax-llm/ax.

This skill helps an LLM generate correct AxFlow workflow code using @ax-llm/ax. Use when the user asks about flow(), AxFlow, workflow orchestration, parallel execution, DAG workflows, conditional routing, map/reduce patterns, or multi-node AI pipelines.

This skill helps an LLM generate correct AxGen code using @ax-llm/ax. Use when the user asks about ax(), AxGen, generators, forward(), streamingForward(), assertions, field processors, step hooks, self-tuning, or structured outputs.

This skill helps an LLM generate correct AxGEPA optimization code using @ax-llm/ax. Use when the user asks about AxGEPA, GEPA, Pareto optimization, multi-objective prompt tuning, reflective prompt evolution, validationExamples, maxMetricCalls, or optimizing a generator, flow, or agent tree.

This skill helps an LLM generate correct AxLearn code using @ax-llm/ax. Use when the user asks about self-improving agents, trace-backed learning, feedback-aware updates, or AxLearn modes.

This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.

Delegate bounded Codex work to an authenticated teammate with recipient-controlled scope and native confirmation.

Use when changing agentd Chronicle capture, privacy, local storage, permissions, policy sync, Secret Broker, or Platform contract behavior.

Security testing and red-teaming for LLMs using NVIDIA's garak vulnerability scanner. Use when probing AI models for jailbreaks, prompt injections, data leakage, toxic content generation, or other failure modes. Triggers on "test LLM security", "red team model", "run garak", "LLM vulnerability scan", "jailbreak testing", or "prompt injection test".